DINOv3-Diffusion Policy: Self-Supervised Large Visual Model for Visuomotor Diffusion Policy Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911168373719040 |
|---|---|
| author | Egbe, ThankGod Wang, Peng Guo, Zhihao Chen, Zidong |
| author_facet | Egbe, ThankGod Wang, Peng Guo, Zhihao Chen, Zidong |
| contents | This paper evaluates DINOv3, a recent large-scale self-supervised vision backbone, for visuomotor diffusion policy learning in robotic manipulation. We investigate whether a purely self-supervised encoder can match or surpass conventional supervised ImageNet-pretrained backbones (e.g., ResNet-18) under three regimes: training from scratch, frozen, and finetuned. Across four benchmark tasks (Push-T, Lift, Can, Square) using a unified FiLM-conditioned diffusion policy, we find that (i) finetuned DINOv3 matches or exceeds ResNet-18 on several tasks, (ii) frozen DINOv3 remains competitive, indicating strong transferable priors, and (iii) self-supervised features improve sample efficiency and robustness. These results support self-supervised large visual models as effective, generalizable perceptual front-ends for action diffusion policies, motivating further exploration of scalable label-free pretraining in robotic manipulation. Compared to using ResNet18 as a backbone, our approach with DINOv3 achieves up to a 10% absolute increase in test-time success rates on challenging tasks such as Can, and on-the-par performance in tasks like Lift, PushT, and Square. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17684 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DINOv3-Diffusion Policy: Self-Supervised Large Visual Model for Visuomotor Diffusion Policy Learning Egbe, ThankGod Wang, Peng Guo, Zhihao Chen, Zidong Computer Vision and Pattern Recognition Robotics This paper evaluates DINOv3, a recent large-scale self-supervised vision backbone, for visuomotor diffusion policy learning in robotic manipulation. We investigate whether a purely self-supervised encoder can match or surpass conventional supervised ImageNet-pretrained backbones (e.g., ResNet-18) under three regimes: training from scratch, frozen, and finetuned. Across four benchmark tasks (Push-T, Lift, Can, Square) using a unified FiLM-conditioned diffusion policy, we find that (i) finetuned DINOv3 matches or exceeds ResNet-18 on several tasks, (ii) frozen DINOv3 remains competitive, indicating strong transferable priors, and (iii) self-supervised features improve sample efficiency and robustness. These results support self-supervised large visual models as effective, generalizable perceptual front-ends for action diffusion policies, motivating further exploration of scalable label-free pretraining in robotic manipulation. Compared to using ResNet18 as a backbone, our approach with DINOv3 achieves up to a 10% absolute increase in test-time success rates on challenging tasks such as Can, and on-the-par performance in tasks like Lift, PushT, and Square. |
| title | DINOv3-Diffusion Policy: Self-Supervised Large Visual Model for Visuomotor Diffusion Policy Learning |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2509.17684 |